Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, but the description adds non-derivable behavior: it is deterministic, makes no API call, costs no credits, and is instant. It also discloses the return shape (recommended + suggestedParams pass-through, runnerUp, 'honest' consider caveats such as a model not actually being cheaper) — meaningful for a tool with no output schema, and it points to antix://models for the live guide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core claim and the cost/latency reassurance, then cleanly sectioned into Inputs / Returns / Quick map. It runs long and the hardcoded model map partially duplicates what the tool computes at runtime (and may drift from the antix://models resource), but every block is scannable and purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter tool with no output schema, it supplies the two things an agent most needs: when to invoke it and what comes back (recommended, runnerUp, caveats, notes). Minor gaps remain — quality/resolution/aspectRatio semantics are left to the schema — but nothing blocks a correct call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 85%, so the schema already carries most parameter meaning; the description mainly restates a subset (kind, useCase, priorities, needsImg2img, needsAudio, duration, count). It adds some value with concrete free-text useCase examples, but omits quality, resolution, aspectRatio and the three reference-flag params entirely, so it does not extend much beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'deterministic model routing' that returns which image/video model fits and the exact params — and explicitly positions itself upstream of antix_generate_image / antix_generate_video, so it is unmistakable against its siblings. An agent knows this is a decision tool, not a generation tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('whenever the user hasn't named a model and the choice isn't obvious, or when they ask which model should I use') and an implicit exclusion (if the user named a model, skip it). The 'FREE (no credits, no API call, instant)' note removes the usual hesitation about calling a helper tool, which is exactly the routing guidance an agent needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.